Skip to main content
HUMAN-AI-TEAMING5 MIN READ

AI review battlecards

Use short battlecard responses to keep AI-assisted work reviewable and accountable.

battlecard AI already checked that. A source-sensitive claim is about to pass through. Your line Great. What source did it check against, and does that source cover this exact case? Do not accept "the model checked" as a source. It moves from model confidence to evidence coverage, which is the real verification question. Can you just make it sound more executive? A draft has weak evidence but the team asks for polish. Yes, after we separate claims from assumptions. Polish should not hide what is still unverified. Do not improve the prose before exposing the risk. It uses AI's language…

Read the full lesson

Sign up free — one personalized lesson every day, matched to your role and goals.

Already have an account? Sign in

← Back to library